This file was created by the TYPO3 extension bib --- Timezone: UTC Creation date: 2024-12-03 Creation time: 15-17-48 --- Number of references 12 article 2016-kunz-tomacs-horizon Parallel Expanded Event Simulation of Tightly Coupled Systems ACM Transactions on Modeling and Computer Simulation (TOMACS) 2016 1 26 2 12:1--12:26 The technical evolution of wireless communication technology and the need for accurately modeling these increasingly complex systems causes a steady growth in the complexity of simulation models. At the same time, multi-core systems have become the de facto standard hardware platform. Unfortunately, wireless systems pose a particular challenge for parallel execution due to a tight coupling of network entities in space and time. Moreover, model developers are often domain experts with no in-depth understanding of parallel and distributed simulation. In combination, both aspects severely limit the performance and the efficiency of existing parallelization techniques. We address these challenges by presenting parallel expanded event simulation, a novel modeling paradigm that extends discrete events with durations which span a period in simulated time. The resulting expanded events form the basis for a conservative synchronization scheme that considers overlapping expanded events eligible for parallel processing. We furthermore put these concepts into practice by implementing Horizon, a parallel expanded event simulation framework specifically tailored to the characteristics of multi-core systems. Our evaluation shows that Horizon achieves considerable speedups in synthetic as well as real-world simulation models and considerably outperforms the current state-of-the-art in distributed simulation. Parallel discrete event simulation, Multi-core Systems, Wireless Systems, Simulation Modeling Paradigm, Conservative Synchronization horizon ACM en 10.1145/2832909 1 GeorgKunz MirkoStoffers OlafLandsiedel KlausWehrle JamesGross inproceedings 2015-stoffers-mswim-data-deps Data Dependency based Parallel Simulation of Wireless Networks 2015 11 2 291-300 Simulation of wireless systems is highly complex and can only be efficient if the simulation is executed in parallel. To this end, independent events have to be identified to enable their simultaneous execution. Hence, the number of events identified as independent needs to be maximized in order to increase the level of parallelism. Traditionally, dependencies are determined only by time and location of events: If two events take place on the same simulation entity, they must be simulated in timestamp order. Our approach to overcome this limitation is to also investigate data-dependencies between events. This enables event reordering and parallelization even for events at the same simulation entity. To this end, we design the simulation language PSimLa, which aids this process. In this paper, we discuss the PSimLa design and compiler as well as our data-dependency analysis approach in detail and present case studies of wireless network models, speeded up by a factor of 10 on 12 cores where time-based parallelization only achieves a 1.6x speedup. Best Paper Award Parallel simulation; Static code analysis; Data dependencies horizon http://www.comsys.rwth-aachen.de/fileadmin/papers/2015/2015-stoffers-mswim-data-deps.pdf Online ACM
New York, NY
Proceedings of the 18th ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems, Cancún, Mexico (MSWiM'15) Cancún, Mexico en 10.1145/2811587.2811593 1 MirkoStoffers TorstenSehy JamesGross KlausWehrle
inproceedings 2015-stoffers-pads-data-deps Analyzing Data Dependencies for Increased Parallelism in Discrete Event Simulation 2015 6 10 73-74 horizon http://www.comsys.rwth-aachen.de/fileadmin/papers/2015/2015-stoffers-pads-data-deps.pdf Online ACM
New York, NY
Proceedings of the 3rd ACM SIGSIM/PADS Conference on Principles of Advanced Discrete Simulation (SIGSIM-PADS’15), London, United Kingdom London, United Kingdom en 10.1145/2769458.2769487 1 MirkoStoffers TorstenSehy JamesGross KlausWehrle
inproceedings 2014-stoffers-simutools-distributed-horizon Large-Scale Network Simulation: Leveraging the Strengths of Modern SMP-based Compute Clusters 2014 3 17 31-40 horizon http://www.comsys.rwth-aachen.de/fileadmin/papers/2014/2014-stoffers-simutools-distributed-horizon.pdf Online ICST
Brussels, Belgium
Proceedings of the 7th International ICST Conference on Simulation Tools and Techniques (SIMUTools'14), Lisbon, Portugal Lisbon, Portugal en 978-1-63190-007-5 10.4108/icst.simutools.2014.254622 1 MirkoStoffers SaschaSchmerling GeorgKunz JamesGross KlausWehrle
article 2012-stoffers-pik-probabilistic-sync Behavior-aware Probabilistic Synchronization in Parallel Simulations and the Influence of the Simulation Model Praxis der Informationsverarbeitung und Kommunikation (PIK Journal) 2012 11 35 4 297--304 horizon http://www.comsys.rwth-aachen.de/fileadmin/papers/2012/2012-stoffers-probabilistic-sync.pdf http://www.degruyter.com/view/j/piko-2012-35-issue-4/pik-2012-0042/pik-2012-0042.xml?format=INT Print Otto Spaniol De Gruyter en 0930-5157 10.1515/pik-2012-0042 MirkoStoffers inproceedings 2012-kunz-pads-gpu Multi-level Parallelism for Time- and Cost-efficient Parallel Discrete Event Simulation on GPUs 2012 7 20 23--32 horizon https://www.comsys.rwth-aachen.de/fileadmin/papers/2012/2012-kunz-pads-gpu.pdf Print IEEE Proceedings of the 26th ACM/IEEE/SCS Workshop on Principles of Advanced and Distributed Simulation (PADS'12), Zhangjiajie, China en 978-0-7695-4714-5 1087-4097 10.1109/PADS.2012.27 1 GeorgKunz DanielSchemmel JamesGross KlausWehrle poster 2012-kunz-omnetpp-sequencechart Poster Abstract: Extending the OMNeT++ Sequence Chart for Supporting Parallel Simulations in Horizon 2012 3 23 5th International Workshop on OMNeT++ (OMNeT++'12), Desenzano del Garda, Italy horizon https://www.comsys.rwth-aachen.de/fileadmin/papers/2012/2012-kunz-omnetpp-sequencechart.pdf Online ICST 5th International Workshop on OMNeT++ (OMNeT++'12), Desezano del Garda, Italy en 1 GeorgKunz SimonTenbusch JamesGross KlausWehrle inproceedings 2012-kunz-simutools-probabilistic-sync Know Thy Simulation Model: Analyzing Event Interactions for Probabilistic Synchronization in Parallel Simulations 2012 3 20 119-128 horizon https://www.comsys.rwth-aachen.de/fileadmin/papers/2012/2012-kunz-simutools-prob-synch.pdf Online ICST
Brussels, Belgium
Proceedings of the 5th International ICST Conference on Simulation Tools and Techniques (SIMUTools'12), Desenzano del Garda, Italy Desenzano, Italy en 978-1-4503-1510-4 10.4108/icst.simutools.2012.247716 1 GeorgKunz MirkoStoffers JamesGross KlausWehrle
inproceedings 2011-kunz-mascots-performance-prediction Predicting Runtime Performance Bounds of Expanded Parallel Discrete Event Simulations 2011 7 25 359 - 368 horizon fileadmin/papers/2011/2011-kunz-performance-prediction-mascots.pdf Online IEEE Computer Society
Los Alamitos, CA, USA
Proceedings of the 19th Annual Meeting of the IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS'11), Singapore Singapore 19th Annual Meeting of the IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems July 25-17, 2011 en 978-1-4577-0468-0 1526-7539 10.1109/MASCOTS.2011.15 1 GeorgKunz SimonTenbusch JamesGross KlausWehrle
inproceedings 2011-kunz-omnetpp-horizon Runtime Efficient Event Scheduling in Multi-threaded Network Simulation 2011 3 21 359-366 Developing an efficient parallel simulation framework for multiprocessor systems is hard. A primary concern is the considerable amount of parallelization overhead imposed on the event handling routines of the simulation framework. Besides more complex event scheduling algorithms, the main sources of overhead are thread synchronization and locking of shared data structures. As a result, the overhead of parallelization may easily outweigh the benefits of parallelization in comparison to classic sequential simulation. We introduce two efficient event handling schemes based on our parallel-simulation extension Horizon for the OMNeT++ simulator.First, we present a \emph{push-based event handling scheme} to minimize the overhead of thread synchronization and locking. Second, we complement this scheme with a novel \emph{event scheduling algorithm} that significantly reduces the overhead of parallel event scheduling. Lastly, we prove the correctness of our scheduling algorithm. Our evaluation reveals a total reduction in the event handling overhead of up to 16x when combining both schemes. horizon fileadmin/papers/2011/2011-kunz-horizon-omnetworkshop.pdf Online ICST
Brussels, Belgium
Proceedings of the 4th International Workshop on OMNeT++ (OMNeT++'11), Barcelona, Spain Barcelona, Spain 4th International Workshop on OMNeT++ (OMNeT++'11) March 21, 2011 en 978-1-936968-00-8 10.4108/icst.simutools.2011.245504 1 GeorgKunz MirkoStoffers JamesGross KlausWehrle
inproceedings 2010-kunz-mascots-horizon Expanding the Event Horizon in Parallelized Network Simulations 2010 8 18 172-181 The simulation models of wireless networks rapidly increase in complexity to accurately model wireless channel characteristics and the properties of advanced transmission technologies. Such detailed models typically lead to a high computational load per simulation event that accumulates to extensive simulation runtimes. Reducing runtimes through parallelization is challenging since it depends on detecting causally independent events that can execute concurrently. Most existing approaches base this detection on lookaheads derived from channel propagation latency or protocol characteristics. In wireless networks, these lookaheads are typically short, causing the potential for parallelization and the achievable speedup to remain small. This paper presents Horizon, which unlocks a substantial portion of a simulation model's workload for parallelization by going beyond the traditional lookahead. We show how to augment discrete events with durations to identify a much larger horizon of independent simulation events and efficiently schedule them on multi-core systems. Our evaluation shows that this approach can significantly cut down the runtime of simulations, in particular for complex and accurate models of wireless networks. horizon fileadmin/papers/2010/2010-kunz-mascots-horizon.pdf Online IEEE Computer Society
Los Alamitos, CA, USA
Proceedings of the 18th Annual Meeting of the IEEE/ACM International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS'10), Miami, FL, USA Miami, FL, USA 18th Annual Meeting of the IEEE/ACM International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS'10) August 17-19, 2010 en 978-0-7695-4197-6 1526-7539 10.1109/MASCOTS.2010.26 1 GeorgKunz OlafLandsiedel JamesGross StefanGötz FarshadNaghibi KlausWehrle
inproceedings 2009-kunz-mascots-horizon Poster Abstract: Horizon - Exploiting Timing Information for Parallel Network Simulation 2009 9 21 575-577 This paper presents Horizon, an extension to network simulation that enables the efficient and detailed simulation of wireless networks. Our contributions are two-fold as Horizon provides i) an API for accurately modeling processing time of discrete event simulation models by augmenting events with time spans and ii) a lightweight parallelization scheme that utilizes timing information to guide the parallel execution of simulations on multi-core computers. In this paper we primarily focus on the latter. horizon fileadmin/papers/2009/2009-kunz-mascots-horizon.pdf Poster Online IEEE Computer Society
Los Alamitos, CA, USA
Proceedings of the 17th Annual Meeting of the IEEE International Symposium on Modelling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS'09), London, UK London, Great Britain 17th Annual Meeting of the IEEE International Symposium on Modelling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS'09) September 21-32, 2009 en 978-1-4244-4926-2 1526-7539 10.1109/MASCOT.2009.5366710 1 GeorgKunz OlafLandsiedel KlausWehrle